Logistic Regression Analysis on YouTube for predicting the popularity of videos based in Python

Consuming and watching videos in YouTube is an integral part of our daily lives. Predicting videos popularity is of great importance for many services and application ranging from supporting the design and evaluation of a wide range of systems, including the targeted advertising to earn more money, ensure an effective search and recommendation systems, and design an effective caching system. The goal of this paper is to use machine learning techniques to predict the popularity of YouTube videos. Here, we present two simple models from machine learning for predicting the popularity of videos based on videos parameters and the proposed popularity function. The experimental results on YouTube provide a good accuracy of popularity prediction and show the performance of our approach.